Model
Trends
.ai
Model
Trends
.ai
최고의 오픈 소스 AI 모델

ComfyUI의 Primitive, Reroute, Note and Group nodes 노드

Primitive nodes share one value (seed, steps, prompt text, resolution) across many nodes, Reroute tidies wires, Notes document the graph and Groups let you bypass or mute whole sections at once.
노드 팩: ComfyUI core
카테고리: 유틸리티와 워크플로 도우미
이 페이지는 아직 번역되지 않아 영어로 표시됩니다.

Primitive, Reroute, Note and Group nodes이(가) 하는 일

Any widget on a node can be converted to an input (right-click > Convert widget to input, or drag from the input dot on the new frontend). A Primitive node connected to that input then drives the value and can feed several nodes at once: one seed for two samplers, one width/height for the latent and the ControlNet resize, one prompt for the base and the detailer pass. Primitive nodes adopt the type of what they connect to (INT, FLOAT, STRING, COMBO) and keep the control_after_generate option for seeds.
Reroute nodes are dots that bend a wire so long links can run around groups. Notes (and Markdown Notes) hold instructions inside the workflow. Groups (right-click canvas > Add Group, or select nodes and Ctrl+G) frame related nodes; with the rgthree Fast Groups Bypasser or the core group right-click menu you can bypass (Ctrl+B) or mute (Ctrl+M) everything inside, turning optional stages on and off.

입력

이름
타입
의미
(converted widget)
any
A Primitive connects to a widget converted to an input and adopts its type.

출력

이름
타입
의미
value
INT / FLOAT / STRING / COMBO
The shared value.
AD
설치는 건너뛰세요: 클라우드에 미리 설치된 ComfyUI 워크플로
BitVector는 완성된 ComfyUI 워크플로를 자체 GPU에서 실행합니다. 설치 없음, 누락 노드 없음, 빨간 박스 없음. 휴대폰이나 노트북에서 열고 1분 안에 생성하세요.

Primitive, Reroute, Note and Group nodes 사용법

  1. Right-click KSampler and convert the seed widget to an input.
  2. Add a Primitive node and connect it to the seed input; set control_after_generate to randomize or fixed.
  3. Connect the same Primitive to a second sampler for an identical seed in a hires pass.
  4. Select the hires nodes and press Ctrl+G to make a group; title it.
  5. Press Ctrl+B with the group selected to bypass it when you want a quick preview.

설정과 팁

  • Bypass (purple) passes the input through unchanged; Mute (grey) stops execution of that branch.
  • The new frontend lets you drag a link from an input onto empty canvas to create a matching Primitive instantly.
  • Use a STRING Primitive as a shared prompt between the main pass and FaceDetailer.
  • Collapse nodes (click the dot top-left) to save space; the wires stay connected.
  • Ctrl+Shift+V pastes nodes with their incoming links intact.

Primitive, Reroute, Note and Group nodes 문제 해결

Primitive refuses to connect

원인
The target widget was not converted to an input, or the Primitive already has a different type.

해결 방법
Convert the widget first; use a fresh Primitive for each type.

Seed changes on every run even with fixed

원인
control_after_generate on the Primitive is randomize, or another node still has its own seed widget.

해결 방법
Set the Primitive to fixed and connect all seed inputs to it.

Bypassed group still runs

원인
Only some nodes were inside the group frame when bypassing.

해결 방법
Resize the group to enclose the nodes, or select them all and press Ctrl+B.

AD
이 워크플로를 휴대폰에서 실행하세요
이 페이지의 모든 워크플로는 모델과 커스텀 노드까지 갖춘 채 BitVector에 미리 설치되어 있습니다. 하나 고르고 프롬프트를 입력하면 끝. 설정 제로, 다운로드 없음.

Primitive, Reroute, Note and Group nodes에 관한 질문

What is the difference between bypass and mute?

Bypass keeps the data flowing as if the node were a wire; mute blocks it, so downstream nodes that need its output cannot run.

Are Reroutes needed?

No, they are cosmetic. The new frontend can also hide links (link visibility toggle).

관련 노드

KSampler
ComfyUI core
KSampler runs the denoising loop: it takes the model, prompts and a latent and produces the finished latent image, controlled by seed, steps, cfg, sampler, scheduler and denoise.
CLIP Text Encode (Prompt)
ComfyUI core
CLIP Text Encode turns a text prompt into CONDITIONING using the model text encoder. One node holds the positive prompt, a second one the negative prompt.
Empty Latent Image
ComfyUI core
Empty Latent Image creates the blank latent canvas (width, height, batch_size) that text-to-image sampling starts from; dimensions must be multiples of 8 and match the model family.
Power Lora Loader (rgthree)
rgthree-comfy
Power Lora Loader stacks any number of LoRAs in one node with per-row toggles and strengths, replacing chains of Load LoRA nodes; the rgthree pack also adds Fast Groups Bypasser, Context nodes and the Image Comparer.
AD
노드 고치기에 지치셨나요? 클라우드에 맡기세요
BitVector는 수백 개의 ComfyUI 워크플로를 빠른 클라우드 GPU에 설치하고 업데이트하고 테스트해 둡니다. Python도, CUDA 오류도, VRAM 한계도 없습니다. 어떤 브라우저에서든 됩니다.

더 많은 ComfyUI 노드

ComfyUI Manager
ComfyUI-Manager
ComfyUI Manager is the extension that installs, updates and fixes custom node packs and models from inside the interface, resolves missing nodes in imported workflows and snapshots your setup.
Load Checkpoint
ComfyUI core
Load Checkpoint (CheckpointLoaderSimple) opens a .safetensors or .ckpt model file and hands out the three parts every workflow needs: the diffusion MODEL, the CLIP text encoder and the VAE.
Save Image
ComfyUI core
Save Image writes the IMAGE tensor to ComfyUI/output as a PNG, with the whole workflow embedded in the file metadata so the picture can be dragged back into ComfyUI to restore the graph.
VAE Decode
ComfyUI core
VAE Decode converts the sampled LATENT into a pixel IMAGE with the VAE; VAE Decode (Tiled) does the same in tiles for very large images.
Load Image
ComfyUI core
Load Image reads a picture from the ComfyUI input folder (or an upload) and outputs an IMAGE tensor plus a MASK taken from the alpha channel, the starting point for img2img, inpainting, ControlNet and IP-Adapter graphs.
Load LoRA
ComfyUI core
Load LoRA (LoraLoader) applies a LoRA file to the MODEL and CLIP with separate strengths, so a style, character or concept can be added to any checkpoint without merging.